采用边缘信息的屏幕图像质量评价

Screen Content Image Quality Assessment Using Edge Information

考虑到人类视觉系统(HVS)对边缘信息比较敏感且屏幕图像中包含大量边缘信息,本文提出采用边缘信息的屏幕图像质量评价方法。该方法首先从空域和频域分别提取参考和失真屏幕图像的边缘信息进而得到边缘信息相似度图,接着基于边缘信息提取屏幕图像中人眼感兴趣区域,最后利用感兴趣区域加权对所得边缘相似度图进行融合计算以获取最终评价分数值。实验结果表明所提算法具有较高的图像质量评价主客观一致性,其性能优于多个最新图像质量评价方法。

Based on the observation that the human visual system （HVS） is very sensitive to the edge information and the screen content image （SCI） contains a lot of edge information, a new image quality assessment method for the SCI is pres- ented by using the edge information in this paper. Firstly, the proposed method individually extracts the edge information of the reference SC1 and its distorted version from the spatial and frequency domains and further combines them to compute the edge information similarity map. Then, the interest region by human eye in the SCI is established based on the edge infor- mation. Finally, the obtained interest region is used as the weighting map to pool the edge information similarity map for generating the final SCI quality score. Experimental results have shown that the proposed method is able to achieve a high correlation with the subiective prediction and is superior to multiple state-of-the-art image quality assessment methods.